NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent.
To run this test with the Phoronix Test Suite , the basic command is: phoronix-test-suite benchmark ncnn .
Test Created 18 September 2020
Last Updated 1 August 2023
Test Type System
Average Install Time 1 Minute, 27 Seconds
Average Run Time 20 Minutes, 48 Seconds
Test Dependencies CMake + C/C++ Compiler Toolchain + Vulkan
Accolades 60k+ Downloads Public Result Uploads * Reported Installs ** Reported Test Completions ** Test Profile Page Views *** OpenBenchmarking.org Events NCNN Popularity Statistics pts/ncnn 2020.09 2020.11 2021.01 2021.03 2021.05 2021.07 2021.09 2021.11 2022.01 2022.03 2022.05 2022.07 2022.09 2022.11 2023.01 2023.03 2023.05 2023.07 2023.09 2023.11 2024.01 2024.03 2024.05 2024.07 2024.09 7K 14K 21K 28K 35K
* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly. ** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform. *** Test profile page view reporting began March 2021. Data updated weekly as of 4 October 2024.
CPU 61.8% Vulkan GPU 38.2% Target Option Popularity OpenBenchmarking.org
yolov4-tiny 5.8% shufflenet-v2 5.9% mobilenet-v3 5.6% vgg16 5.9% efficientnet-b0 5.9% regnety_400m 5.9% googlenet 5.9% FastestDet 5.8% alexnet 5.9% mobilenet 5.9% resnet18 5.9% resnet50 5.9% vision_transformer 5.9% blazeface 5.9% mobilenet-v2 5.9% squeezenet_ssd 5.9% mnasnet 5.9% Model Option Popularity OpenBenchmarking.org
Revision Historypts/ncnn-1.5.0 [View Source ] Tue, 01 Aug 2023 11:49:36 GMT Update against latest upstream.
pts/ncnn-1.4.0 [View Source ] Sat, 13 Aug 2022 09:59:41 GMT Update against NCNN 20220729 upstream.
pts/ncnn-1.3.0 [View Source ] Tue, 27 Jul 2021 16:34:42 GMT Update against NCNN 2021-07-20 upstream, fix possible Vulkan build issue by including glslang source tree.
pts/ncnn-1.2.0 [View Source ] Fri, 18 Jun 2021 08:11:33 GMT Update against NCNN 20210525 release.
pts/ncnn-1.1.0 [View Source ] Fri, 18 Dec 2020 08:06:41 GMT Update against new upstream NCNN 20201218.
pts/ncnn-1.0.3 [View Source ] Fri, 25 Sep 2020 06:36:39 GMT Drop int8 tests per https://github.com/phoronix-test-suite/test-profiles/pull/167
pts/ncnn-1.0.2 [View Source ] Thu, 24 Sep 2020 12:52:47 GMT Expose Vulkan GPU support.
pts/ncnn-1.0.1 [View Source ] Fri, 18 Sep 2020 12:28:10 GMT Increase the run count.
pts/ncnn-1.0.0 [View Source ] Fri, 18 Sep 2020 11:58:15 GMT Initial commit of Tencent NCNN.
Performance MetricsAnalyze Test Configuration: pts/ncnn-1.5.x - Target: CPU - Model: googlenet pts/ncnn-1.5.x - Target: CPU - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: CPU - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: CPU - Model: alexnet pts/ncnn-1.5.x - Target: CPU - Model: regnety_400m pts/ncnn-1.5.x - Target: CPU - Model: resnet18 pts/ncnn-1.5.x - Target: CPU - Model: mobilenet pts/ncnn-1.5.x - Target: CPU - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: CPU - Model: vgg16 pts/ncnn-1.5.x - Target: CPU - Model: resnet50 pts/ncnn-1.5.x - Target: CPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: CPU - Model: blazeface pts/ncnn-1.5.x - Target: CPU - Model: vision_transformer pts/ncnn-1.5.x - Target: CPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.x - Target: CPU - Model: mnasnet pts/ncnn-1.5.x - Target: CPU - Model: FastestDet pts/ncnn-1.5.x - Target: CPU - Model: yolov4-tiny pts/ncnn-1.5.x - Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.5.x - Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.5.x - Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.5.x - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU - Model: mobilenet pts/ncnn-1.5.x - Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.5.x - Target: Vulkan GPU - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: Vulkan GPU - Model: alexnet pts/ncnn-1.5.x - Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: Vulkan GPU - Model: regnety_400m pts/ncnn-1.5.x - Target: Vulkan GPU - Model: vision_transformer pts/ncnn-1.5.x - Target: Vulkan GPU - Model: googlenet pts/ncnn-1.5.x - Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.5.x - Target: Vulkan GPU - Model: blazeface pts/ncnn-1.5.x - Target: Vulkan GPU - Model: FastestDet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: alexnet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: vision_transformer pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: resnet50 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: vgg16 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: mnasnet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: blazeface pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: googlenet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: mobilenet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: yolov4-tiny pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: resnet18 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: FastestDet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: alexnet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: resnet50 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: blazeface pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: vgg16 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: mnasnet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: vision_transformer pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: regnety_400m pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: resnet18 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: googlenet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: mobilenet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: yolov4-tiny pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: CPU-v3-v3-v3 - Model: FastestDet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3 - Model: regnety_400m pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.x - Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: alexnet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: vision_transformer pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: mobilenet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: resnet18 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: regnety_400m pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: googlenet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: blazeface pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: FastestDet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: mnasnet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: vgg16 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: resnet50 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vgg16 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: regnety_400m pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: FastestDet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet50 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: alexnet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vision_transformer pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet18 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: blazeface pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: googlenet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mnasnet pts/ncnn-1.5.x - Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: vgg16 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: resnet18 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: FastestDet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: mnasnet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v2 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b0 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: mobilenet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: resnet50 pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: blazeface pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: regnety_400m pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: googlenet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: alexnet pts/ncnn-1.5.x - Target: CPU-v3-v3-v3-v3-v3-v3 - Model: vision_transformer pts/ncnn-1.4.x - Target: CPU - Model: vision_transformer pts/ncnn-1.4.x - Target: CPU - Model: resnet50 pts/ncnn-1.4.x - Target: CPU - Model: vgg16 pts/ncnn-1.4.x - Target: CPU - Model: resnet18 pts/ncnn-1.4.x - Target: CPU - Model: mobilenet pts/ncnn-1.4.x - Target: CPU - Model: alexnet pts/ncnn-1.4.x - Target: CPU - Model: squeezenet_ssd pts/ncnn-1.4.x - Target: CPU - Model: yolov4-tiny pts/ncnn-1.4.x - Target: CPU - Model: regnety_400m pts/ncnn-1.4.x - Target: CPU - Model: googlenet pts/ncnn-1.4.x - Target: CPU - Model: efficientnet-b0 pts/ncnn-1.4.x - Target: CPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.4.x - Target: CPU - Model: blazeface pts/ncnn-1.4.x - Target: CPU - Model: shufflenet-v2 pts/ncnn-1.4.x - Target: CPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.4.x - Target: CPU - Model: mnasnet pts/ncnn-1.4.x - Target: CPU - Model: FastestDet pts/ncnn-1.4.x - Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: vision_transformer pts/ncnn-1.4.x - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: mobilenet pts/ncnn-1.4.x - Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.4.x - Target: Vulkan GPU - Model: alexnet pts/ncnn-1.4.x - Target: Vulkan GPU - Model: blazeface pts/ncnn-1.4.x - Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: regnety_400m pts/ncnn-1.4.x - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.4.x - Target: Vulkan GPU - Model: googlenet pts/ncnn-1.4.x - Target: Vulkan GPU - Model: FastestDet pts/ncnn-1.4.x - Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.4.x - Target: Vulkan GPU - Model: squeezenet_ssd pts/ncnn-1.3.x - Target: CPU - Model: resnet50 pts/ncnn-1.3.x - Target: CPU - Model: squeezenet_ssd pts/ncnn-1.3.x - Target: CPU - Model: mobilenet pts/ncnn-1.3.x - Target: CPU - Model: vgg16 pts/ncnn-1.3.x - Target: CPU - Model: alexnet pts/ncnn-1.3.x - Target: CPU - Model: yolov4-tiny pts/ncnn-1.3.x - Target: CPU - Model: resnet18 pts/ncnn-1.3.x - Target: CPU - Model: shufflenet-v2 pts/ncnn-1.3.x - Target: CPU - Model: regnety_400m pts/ncnn-1.3.x - Target: CPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.3.x - Target: CPU - Model: efficientnet-b0 pts/ncnn-1.3.x - Target: CPU - Model: mnasnet pts/ncnn-1.3.x - Target: CPU - Model: googlenet pts/ncnn-1.3.x - Target: CPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.3.x - Target: CPU - Model: blazeface pts/ncnn-1.3.x - Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.3.x - Target: Vulkan GPU - Model: alexnet pts/ncnn-1.3.x - Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.3.x - Target: Vulkan GPU - Model: squeezenet_ssd pts/ncnn-1.3.x - Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.3.x - Target: Vulkan GPU - Model: regnety_400m pts/ncnn-1.3.x - Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.3.x - Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.3.x - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.3.x - Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.3.x - Target: Vulkan GPU - Model: googlenet pts/ncnn-1.3.x - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.3.x - Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.3.x - Target: Vulkan GPU - Model: blazeface pts/ncnn-1.3.x - Target: Vulkan GPU - Model: mobilenet pts/ncnn-1.2.x - Target: CPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.2.x - Target: CPU - Model: resnet18 pts/ncnn-1.2.x - Target: CPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.2.x - Target: CPU - Model: vgg16 pts/ncnn-1.2.x - Target: CPU - Model: efficientnet-b0 pts/ncnn-1.2.x - Target: CPU - Model: resnet50 pts/ncnn-1.2.x - Target: CPU - Model: blazeface pts/ncnn-1.2.x - Target: CPU - Model: googlenet pts/ncnn-1.2.x - Target: CPU - Model: yolov4-tiny pts/ncnn-1.2.x - Target: CPU - Model: mobilenet pts/ncnn-1.2.x - Target: CPU - Model: squeezenet_ssd pts/ncnn-1.2.x - Target: CPU - Model: mnasnet pts/ncnn-1.2.x - Target: CPU - Model: alexnet pts/ncnn-1.2.x - Target: CPU - Model: shufflenet-v2 pts/ncnn-1.2.x - Target: CPU - Model: regnety_400m pts/ncnn-1.2.x - Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.2.x - Target: Vulkan GPU - Model: mobilenet pts/ncnn-1.2.x - Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.2.x - Target: Vulkan GPU - Model: googlenet pts/ncnn-1.2.x - Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.2.x - Target: Vulkan GPU - Model: regnety_400m pts/ncnn-1.2.x - Target: Vulkan GPU - Model: squeezenet_ssd pts/ncnn-1.2.x - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.2.x - Target: Vulkan GPU - Model: blazeface pts/ncnn-1.2.x - Target: Vulkan GPU - Model: alexnet pts/ncnn-1.2.x - Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.2.x - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.2.x - Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.2.x - Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.2.x - Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.1.x - Target: CPU - Model: efficientnet-b0 pts/ncnn-1.1.x - Target: CPU - Model: resnet50 pts/ncnn-1.1.x - Target: CPU - Model: mobilenet pts/ncnn-1.1.x - Target: CPU - Model: vgg16 pts/ncnn-1.1.x - Target: CPU - Model: squeezenet_ssd pts/ncnn-1.1.x - Target: CPU - Model: alexnet pts/ncnn-1.1.x - Target: CPU - Model: googlenet pts/ncnn-1.1.x - Target: CPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.1.x - Target: CPU - Model: resnet18 pts/ncnn-1.1.x - Target: CPU - Model: regnety_400m pts/ncnn-1.1.x - Target: CPU - Model: shufflenet-v2 pts/ncnn-1.1.x - Target: CPU - Model: mnasnet pts/ncnn-1.1.x - Target: CPU - Model: yolov4-tiny pts/ncnn-1.1.x - Target: CPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.1.x - Target: CPU - Model: blazeface pts/ncnn-1.1.x - Target: Vulkan GPU - Model: regnety_400m pts/ncnn-1.1.x - Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.1.x - Target: Vulkan GPU - Model: alexnet pts/ncnn-1.1.x - Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.1.x - Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.1.x - Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.1.x - Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.1.x - Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.1.x - Target: Vulkan GPU - Model: blazeface pts/ncnn-1.1.x - Target: Vulkan GPU - Model: googlenet pts/ncnn-1.1.x - Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.1.x - Target: Vulkan GPU - Model: mobilenet pts/ncnn-1.1.x - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.1.x - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.1.x - Target: Vulkan GPU - Model: squeezenet_ssd pts/ncnn-1.0.x - Target: CPU - Model: squeezenet pts/ncnn-1.0.x - Target: CPU - Model: alexnet pts/ncnn-1.0.x - Target: CPU - Model: mnasnet pts/ncnn-1.0.x - Target: CPU - Model: blazeface pts/ncnn-1.0.x - Target: CPU - Model: yolov4-tiny pts/ncnn-1.0.x - Target: CPU - Model: resnet18 pts/ncnn-1.0.x - Target: CPU - Model: resnet50 pts/ncnn-1.0.x - Target: CPU - Model: mobilenet pts/ncnn-1.0.x - Target: CPU - Model: googlenet pts/ncnn-1.0.x - Target: CPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.0.x - Target: CPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.0.x - Target: CPU - Model: efficientnet-b0 pts/ncnn-1.0.x - Target: CPU - Model: vgg16 pts/ncnn-1.0.x - Target: CPU - Model: shufflenet-v2 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: alexnet pts/ncnn-1.0.x - Target: Vulkan GPU - Model: yolov4-tiny pts/ncnn-1.0.x - Target: Vulkan GPU - Model: efficientnet-b0 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: resnet50 pts/ncnn-1.0.x - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: vgg16 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: mobilenet pts/ncnn-1.0.x - Target: Vulkan GPU - Model: squeezenet pts/ncnn-1.0.x - Target: Vulkan GPU - Model: resnet18 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: shufflenet-v2 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: mnasnet pts/ncnn-1.0.x - Target: Vulkan GPU - Model: googlenet pts/ncnn-1.0.x - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts/ncnn-1.0.x - Target: Vulkan GPU - Model: blazeface pts/ncnn-1.0.x - Target: CPU - Model: googlenet_int8 pts/ncnn-1.0.x - Target: CPU - Model: vgg16_int8 pts/ncnn-1.0.x - Target: CPU - Model: squeezenet_int8 pts/ncnn-1.0.x - Target: CPU - Model: resnet18_int8 pts/ncnn-1.0.x - Target: CPU - Model: resnet50_int8 pts/ncnn-1.0.x - Target: CPU - Model: mobilenet_v3 pts/ncnn-1.0.x - Target: CPU - Model: mobilenetv2_yolov3 NCNN 20230517 Target: CPU - Model: googlenet OpenBenchmarking.org metrics for this test profile configuration based on 278 public results since 1 August 2023 with the latest data as of 3 October 2024 .
Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.
Component
Percentile Rank
# Compatible Public Results
ms (Average)
OpenBenchmarking.org Distribution Of Public Results - Target: CPU - Model: googlenet 277 Results Range From 3 To 1984 ms 3 48 93 138 183 228 273 318 363 408 453 498 543 588 633 678 723 768 813 858 903 948 993 1038 1083 1128 1173 1218 1263 1308 1353 1398 1443 1488 1533 1578 1623 1668 1713 1758 1803 1848 1893 1938 1983 2028 50 100 150 200 250
Based on OpenBenchmarking.org data, the selected test / test configuration (NCNN 20230517 - Target: CPU - Model: googlenet ) has an average run-time of 27 minutes . By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.
OpenBenchmarking.org Minutes Time Required To Complete Benchmark Target: CPU - Model: googlenet Run-Time 60 120 180 240 300 Min: 2 / Avg: 26.41 / Max: 328
Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 1.1% .
OpenBenchmarking.org Percent, Fewer Is Better Average Deviation Between Runs Target: CPU - Model: googlenet Deviation 8 16 24 32 40 Min: 0 / Avg: 1.11 / Max: 37
Notable Instruction Set Usage Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.
Instruction Set
Support
Instructions Detected
SSE2 (SSE2)
Used by default on supported hardware.
MOVD PSHUFD PSHUFLW MOVDQU MOVDQA SUBSD MOVAPD MINSD MAXSD ADDSD CVTSI2SD DIVSD PUNPCKLQDQ CVTSS2SD MULSD MULPD PSRLDQ CVTSD2SS CVTTPS2DQ CVTDQ2PS PUNPCKHQDQ PMULUDQ PADDQ SHUFPD COMISD PSHUFHW
Used by default on supported hardware. Found on Intel processors since Sandy Bridge (2011). Found on AMD processors since Bulldozer (2011).
VZEROUPPER VBROADCASTSS VPERM2F128 VINSERTF128 VEXTRACTF128 VPERMILPS VMASKMOVPS VBROADCASTF128 VBROADCASTSD
Used by default on supported hardware. Found on Intel processors since Haswell (2013). Found on AMD processors since Excavator (2016).
VPBROADCASTD VINSERTI128 VPERMD VEXTRACTI128 VPERMQ VPERM2I128 VPBROADCASTW VPBROADCASTB VPBROADCASTQ VGATHERDPS VPGATHERQQ VPSRLVQ
Advanced Vector Extensions 512 (AVX512)
Used by default on supported hardware.
(ZMM REGISTER USE)
Used by default on supported hardware. Found on Intel processors since Haswell (2013). Found on AMD processors since Bulldozer (2011).
VFMADD132PS VFMADD132SS VFNMADD231PS VFMADD231PS VFMADD213PS VFNMADD132PS VFNMADD132SS VFNMADD213SS VFMSUB132SS VFNMADD231SS VFMADD231SS VFMSUB132PS VFMSUB231SS VFMADD213SS VFMADD132PD VFMADD132SD VFNMSUB132SS VFNMSUB231SS
AVX Vector Neural Network Instructions (AVX-VNNI)
Requires passing a supported compiler/build flag (verified with targets: tigerlake, cascadelake).
VPDPWSSD
The test / benchmark does honor compiler flag changes.
Last automated analysis: 18 September 2023
This test profile binary relies on the shared libraries libgomp.so.1, libm.so.6, libmvec.so.1, libc.so.6 .
Tested CPU Architectures This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.
CPU Architecture
Kernel Identifier
Verified On
Intel / AMD x86 64-bit
x86_64
(Many Processors)
RISC-V 64-bit
riscv64
SiFive RISC-V, rv64imafdcvsu
Loongson LoongArch 64-bit
loongarch64
(Many Processors)
ARMv7 32-bit
armv7l
ARMv7 Cortex-A72 4-Core
ARMv8 64-bit
arm64
Apple M2 Pro
ARMv8 64-bit
aarch64
ARMv8 Cortex-A72, ARMv8 Cortex-A76 4-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-N2, ARMv8 Neoverse-V1, ARMv8 Neoverse-V2, Apple M2
Recent Test Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 195 Benchmark Results
2 Systems - 19 Benchmark Results
2 x AMD EPYC 9334 32-Core - Giga Computing MZ73-LM1-000 v01000100 - AMD Device 14a4
Ubuntu 22.04 - 6.8.0-45-generic - GNOME Shell 42.9
Featured Graphics Comparison
1 System - 18 Benchmark Results
Unknown - LOONGSON Dabieshan Loongson-TC542F0 - Loongson LLC Hyper Transport Bridge
Anolis OS 23.1 - 6.6.25-2.1.an23.loongarch64 - X Server 1.20.14
1 System - 18 Benchmark Results
2 x Hygon C86 7280 32-core - Suma R6240H0 62DB32 v24002826 - Chengdu Haiguang IC Design Root Complex
Ubuntu 24.04 - 6.8.0-41-generic - GCC 13.2.0
1 System - 47 Benchmark Results
ARMv8 Cortex-A78E - NVIDIA Jetson Orin Nano Developer Kit - 8GB
Ubuntu 22.04 - 5.15.136-tegra - GNOME Shell 42.9
1 System - 47 Benchmark Results
ARMv8 Cortex-A78E - NVIDIA Jetson AGX Orin Developer Kit - 30GB
Ubuntu 22.04 - 5.15.136-tegra - GNOME Shell 42.9
1 System - 334 Benchmark Results
Intel Core i3-12100 - ASRock H610M-HDV/M.2 R2.0 - Intel Device 7aa7
Ubuntu 20.04 - 5.15.0-89-generic - GNOME Shell 3.36.9
Most Popular Test Results
2 Systems - 831 Benchmark Results
Intel Core Ultra 7 155H - MTL Coral_MTH - Intel Device 7e7f
Ubuntu 23.10 - 6.7.0-060700rc5-generic - GNOME Shell 45.1
20 Systems - 173 Benchmark Results
AMD Ryzen 9 7950X 16-Core - ASUS ROG STRIX X670E-E GAMING WIFI - AMD Device 14d8
Ubuntu 23.04 - 6.4.6-060406-generic - GNOME Shell 44.2
Featured Compiler Comparison
Intel Core i7-8565U - Dell 0KTW76 - Intel Cannon Point-LP
Ubuntu 22.04 - 5.19.0-rc6-phx-retbleed - GNOME Shell 42.2
Featured Graphics Comparison
AMD Ryzen 5 4500U - LENOVO LNVNB161216 - AMD Renoir
Pop 22.04 - 5.17.5-76051705-generic - GNOME Shell 42.1
4 Systems - 96 Benchmark Results
2 x Intel Xeon Platinum 8490H - Quanta Cloud S6Q-MB-MPS - Intel Device 1bce
Ubuntu 22.10 - 6.0.0-060000rc3daily20220904-generic - GNOME Shell
2 Systems - 191 Benchmark Results
AMD Ryzen 7 PRO 5850U - HP 8A78 - AMD Renoir
Pop 22.04 - 6.2.6-76060206-generic - GNOME Shell 42.5
3 Systems - 53 Benchmark Results
AMD Ryzen Z1 Extreme - ASUS RC71L v1.0 - AMD Device 14e8
Ubuntu 23.04 - 6.2.0-24-generic - GNOME Shell 44.2
3 Systems - 53 Benchmark Results
AMD Ryzen Threadripper 3990X 64-Core - Gigabyte TRX40 AORUS PRO WIFI - AMD Starship
Ubuntu 23.04 - 6.2.0-26-generic - GNOME Shell 44.0
3 Systems - 369 Benchmark Results
Intel Xeon E-2388G - ASRockRack E3C252D4U - Intel Tiger Lake-H
Ubuntu 22.04 - 6.2.0-26-generic - GNOME Shell 42.9
Featured Kernel Comparison
Intel Core i7-1185G7 - Dell 0DXP1F - Intel Tiger Lake-LP
Ubuntu 22.04 - 6.2.0-36-generic - GNOME Shell 42.2
2 Systems - 358 Benchmark Results
AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship
Ubuntu 22.04 - 6.2.0-35-generic - GNOME Shell 42.2
3 Systems - 87 Benchmark Results
AMD Ryzen 9 7950X 16-Core - ASUS ROG STRIX X670E-E GAMING WIFI - AMD Device 14d8
Ubuntu 23.04 - 6.4.6-060406-generic - GNOME Shell 44.2
2 Systems - 150 Benchmark Results
2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Ice Lake IEH
Ubuntu 22.10 - 6.2.0-rc5-phx-dodt - GNOME Shell 43.0
2 Systems - 147 Benchmark Results
AMD EPYC 9384X 32-Core - AMD Titanite_4G - AMD Device 14a4
Ubuntu 22.04 - 5.15.0-47-generic - GNOME Shell 42.4